6 papers
Physics-Informed Learning for Robust Acoustic Localization with Calibrated Uncertainty
Jennifer N. Kampe, Changwoo J. Lee, Xin Shen +5
Recent advances in Passive Acoustic Monitoring (PAM) offer an opportunity to obtain ecological spatial point-process data at unprecedented scale. However, realizing this opportunit…
ForestIR: Physics-Informed Forest Sound Simulation for Array-Based Bioacoustic Remote Sensing
Xin Shen, Jennifer N. Kampe, Changwoo J. Lee +7
Microphone array-based passive acoustic monitoring is increasingly used for biodiversity sensing in forests. However, design and evaluation of array systems and configurations rema…
Transformers Can Learn Posterior Predictive Distributions In-Context
Gyeonghun Kang, Changwoo J. Lee, Xiang Cheng
Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-c…
Marginally interpretable spatial logistic regression with bridge processes
Changwoo J. Lee, David B. Dunson
In including random effects to account for dependent observations, the odds ratio interpretation of logistic regression coefficients is changed from population-averaged to subject-…
Scalable and robust regression models for continuous proportional data
Changwoo J. Lee, Benjamin K. Dahl, Otso Ovaskainen +1
Beta regression is used routinely for continuous proportional data, but it often encounters practical issues such as a lack of robustness to misspecification of the beta distributi…
Logistic-beta processes for dependent random probabilities with beta marginals
Changwoo J. Lee, Alessandro Zito, Huiyan Sang +1
The beta distribution serves as a canonical tool for modeling probabilities in statistics and machine learning. However, there is limited work on flexible and computationally conve…